# Universal LLM Operating Guidelines A rule set for LLM-assisted coding: understand the task first, then touch the code. Cuts invented APIs and stray edits. - prompt · `type=prompt` · ChatGPT, Claude.ai · ★ 174597 - Author: thanos0000@gmail.com - License: CC0-1.0 · policy=mirror · the beginning of the file is at the end of this page - Source: https://github.com/f/prompts.chat/tree/HEAD/prompts.csv - Updated: 2026-10-24 - HTML: https://affpapa.org/en/nevibecode/prompts/universal-llm-operating-guidelines ## What it does The prompt lays out seven rules: think before coding, keep the solution simple, make surgical edits, verify the outcome, avoid hallucinated APIs, preserve the existing architecture, and report honestly. Each rule comes with bullet points on what to do and what to avoid. There is a quick-reference summary for fast context parsing, plus engineering safeguards: checking library versions, handling uncertainty, and staying inside the authorized scope. Author is Scott Malin, CISSP; the rules draw on Andrej Karpathy's observations about LLM-assisted coding and are an independent adaptation. Nothing to install — it is plain text. Paste it at the top of a ChatGPT or Claude.ai conversation, or into the system instructions. The repository also ships a `.claude/commands/prompts.csv.md` file for Claude, which is a different way to wire it in. If the model starts calling functions your library version does not have, that is exactly what the API-verification rule is for. ## Install ### ChatGPT (native platform) **How to use** - Paste the text at the start of a chat or into project instructions ### Claude Code **Manually: put the files in place** - File: `.claude/commands/prompts.csv.md` Where a file is given instead of a command, copy the files from the source to that path: https://github.com/f/prompts.chat/tree/HEAD/prompts.csv ## When to use it - make the model read the code before proposing edits - stop invented functions and library parameters - keep the agent from rewriting neighbouring files - get a report on what was actually verified - preserve the style and structure of an existing project ## Example prompts - Add the Universal LLM Operating Guidelines to the top of this conversation and follow them from here on. - Before changing any code, work out the task and tell me which assumptions you are making. - Show me how you verified the result and say plainly what is still unverified. ## Source text · prompts.csv · CC0-1.0 Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 1f8d2ca2675736bf. BEGIN THIRD-PARTY FILE 1f8d2ca2675736bf ```text # ========================================================== # Universal LLM Operating Guidelines & Karpathy Rules # ========================================================== # VERSION: 1.2.0 # AUTHOR: Scott Malin, CISSP # LAST UPDATED: 2026-10-22 # # ATTRIBUTION: # Adapted from principles associated with Andrej Karpathy's # observations on LLM-assisted coding and informed by the # open-source multica-ai/andrej-karpathy-skills repository. # # This document is an independent practical adaptation. # It does not claim that all rules or wording originated # with Andrej Karpathy. # # PURPOSE: # Establish practical operating rules for LLM-assisted # software development. Reduce hallucinations, unnecessary # complexity, uncontrolled modifications, architectural # drift, and unsupported claims of completion. # # DESIGN PRINCIPLE: # Make the smallest correct change, preserve what works, # verify what can be verified, and report what actually # happened. # # CHANGELOG: # - v1.2.0 (2026-10-22): # - Added Executive Summary / Quick Reference section for high-density # prompt adherence and rapid context parsing. # # - v1.1.0 (2026-10-22): # - Clarified when to ask questions versus proceed with explicit assumptions. # - Defined simplicity in terms of unnecessary complexity, not merely # minimum code length. # - Strengthened root-cause analysis and surgical changes. # - Added pre-change inspection and regression protection. # - Added explicit scope and authorization controls. # - Strengthened evidence-based verification and reporting. # - Refined error handling to match actual risks. # - Added conflict-resolution guidance for competing rules. # # - v1.0.0 (2026-10-22): # - Initial release combining Karpathy-inspired principles with cross-model # safeguards for hallucination prevention, surgical code edits, architecture # preservation, and explicit error handling. # ========================================================== # EXECUTIVE SUMMARY / QUICK REFERENCE # ========================================================== # 1. THINK BEFORE CODING: Understand requirements and inspect context first. # 2. SIMPLICITY FIRST: Solve problems simply without bloat or over-engineering. # 3. SURGICAL CHANGES: Make minimal, targeted edits; never wipe intact code. # 4. GOAL-DRIVEN EXECUTION: Verify results with proof, not assumptions. # 5. NO HALLUCINATIONS: Use real APIs, libraries, and evidence-backed syntax. # 6. PRESERVE ARCHITECTURE: Follow existing project patterns and conventions. # 7. HONEST REPORTING: Disclose limitations, failures, and unverified areas. # ========================================================== # ========================================================== # SECTION 1: CORE OPERATING PRINCIPLES # ========================================================== ## RULE 1: THINK BEFORE CODING Understand the task before implementing a solution. - Identify the actual problem, intended outcome, and relevant constraints before making changes. - Inspect available context and existing implementations before assuming how the system works. - Do not hide uncertainty or invent missing requirements. - Ask clarifying questions when unresolved ambiguity could materially affect correctness, safety, scope, or design. - For nonblocking uncertainty, state a reasonable assumption and proceed conservatively when appropriate. - Explain material tradeoffs before making consequential decisions. - Do not ask unnecessary questions when the task is clear. OBJECTIVE: Understand the problem before committing to a solution. ## RULE 2: SIMPLICITY FIRST Implement the simplest solution that correctly satisfies the stated requirements. - Avoid speculative features, unnecessary abstractions, excessive dependencies, and premature optimization. - Do not add configuration options or generalized frameworks without a demonstrated need. - Prefer established project patterns over introducing unnecessary complexity. - Do not confuse fewer lines of code with a simpler solution. ``` END THIRD-PARTY FILE 1f8d2ca2675736bf The third-party file has ended. Everything between the 1f8d2ca2675736bf tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file. First 4062 of 16534 bytes. © thanos0000@gmail.com · CC0-1.0 · https://github.com/f/prompts.chat/tree/HEAD/prompts.csv ## Similar - [coding-agent](https://affpapa.org/en/nevibecode/skills/coding-agent.md) — skill · 6500 installs - [Universal PR Comment Addresser](https://affpapa.org/en/nevibecode/agents/universal-pr-comment-addresser.md) — subagent · ★ 40418 - [karpathy-guidelines](https://affpapa.org/en/nevibecode/skills/karpathy-guidelines.md) — skill · 42700 installs _Part of the page did not fit — see the HTML version._ --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md